sosoai/phi-2-ko-mlx
This model was converted to MLX format from daekeun-ml/phi-2-ko-v0.1.
Refer to the original model card for more details on the model.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sosoai/phi-2-ko-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 67
Model size
0.6B params
Tensor type
F16
·
U32
·
Hardware compatibility
Log In
to add your hardware
Quantized